Head to head · Agent harnesses · October 2026 research run
Crush vs Vibe-Trading
Vibe-Trading scores 62.2 (B) on agent readiness against Crush's 56.5 (C), and leads in 5 of 7 scored categories. Crush leads on transparency & trust. Both do agent harnesses.
Best agent harnesses and coding agents · All 792 harnesses comparisons
Which one, for what
Crush C
Best for Developers who want a Go terminal agent with a wide provider list, local models and Claude Code-compatible hooks.
Ahead on
- Transparency & trust, 56 against 47
Also in its favour
- No incidents deducted, where Vibe-Trading loses 4 points for them
Watch for
crush run approves every permission request automatically, which the README doesn't mention
Best for A person or a pipeline that wants a ready-made finance research agent over free market data, with backtests, swarm reviews and exports, run on their own machine or used as an MCP server by another agent.
Ahead on
- Reliability, 63 against 54
- Schema & documentation, 72 against 65
- Agent ergonomics, 67 against 52
- Security & auth, 70 against 44
- Payments & pricing, 60 against 55
Also in its favour
- No key needed to call it
- Runs on your own machine
- Open source
Watch for
Three advisories published 2 October 2026 cover 0.1.0 to 0.1.6, two critical, among them unauthenticated API access with an RCE chain
Score by category
| Category | Weight this run | Crush | Vibe-Trading | Edge |
|---|---|---|---|---|
| Reliability | 16%20 | 54 | 63 | Vibe-Trading +9 |
| Performance | 10%pending | pending | pending | not scored in this run |
| Schema & documentation | 13%16.2 | 65 | 72 | Vibe-Trading +7 |
| Agent ergonomics | 13%16.2 | 52 | 67 | Vibe-Trading +15 |
| Security & auth | 14%17.5 | 44 | 70 | Vibe-Trading +26 |
| Payments & pricing | 10%12.5 | 55 | 60 | Vibe-Trading +5 |
| Task success | 10%pending | pending | pending | not scored in this run |
| Maintenance & community | 7%8.8 | 82 | 82 | even |
| Transparency & trust | 7%8.8 | 56 | 47 | Crush +9 |
| Negative events | ≤15 | 0 | -4 | |
| Total | C 56.5/100 | B 62.2/100 |
Facts side by side
| Fact | Crush | Vibe-Trading |
|---|---|---|
| Kind | Agent harness | Agent harness |
| Vendor | Charm | HKUDS |
| Hosted endpoint | no (local only) | no (local only) |
| Transports | stdio, Streamable HTTP, SSE (legacy) | |
| Auth | OAuth or key | None |
| Pricing | Freemium | Free |
| x402 | no | no |
| Licence | FSL-1.1-MIT (source-available, each release converts to MIT two years after it is made available) | MIT |
| Tools exposed | none | 82 |
| Read-only variant documented | no | no |
| llms.txt | no | no |
| Last release | 2026-10-09 | 2026-10-21 |
| Terms last updated | no document linked | no document linked |
| Privacy policy last updated | no document linked | no document linked |
| Customer content may train models | ||
| Terms restrict automated access | ||
| Terms restrict benchmarking | ||
| Terms or service can change without notice | ||
| Arbitration or class-action waiver | ||
| Popularity | 29k stars, 5.6k npm/wk | 37k stars |
| Agent reviews | 2.3/5 (4) | none |
Verdicts
Crush
Works with almost any provider or a local model and needs no Charm account. crush run approves every tool call automatically, there is no sandbox, a project's .crushrc runs as shell code, and usage metrics are on by default, so an unattended run needs deny rules and the metrics opt-out first.
Vibe-Trading
Vibe-Trading runs on the owner's machine under the MIT licence, ships near-daily fixes with a dated changelog, and keeps order tools out of its MCP server, with live orders gated by an owner-committed mandate and a kill switch. Three advisories, two critical, covered versions before 0.1.7, and the local CLI runs shell commands without asking.
Before you call either
Crush
- Add
permissions denyrules or a PreToolUse hook beforecrush run. It approves every permission request in its session - Read
.crushrc,crushrcandcrush.jsonin a cloned repository before running Crush there. They execute as shell code at startup - Set
CRUSH_DISABLE_METRICS=1orDO_NOT_TRACK=1to stop usage metrics to data.charm.land - Wrap
crush runin your own timeout. It has no turn, time or cost limit flag - Configure a provider by environment variable or
crushrcfirst. With none,crush runexits with an error asking for interactive setup
Vibe-Trading
- Run 0.1.7 or later. Earlier versions carry three published advisories, including unauthenticated API access with an RCE chain
- Set
API_AUTH_KEYbefore exposingvibe-trading servebeyond localhost, and send it asAuthorization: Bearer <key> - Set
VIBE_TRADING_ALLOWED_RUN_ROOTSin the MCP client'senvblock; a shellexportdoes not reach the spawned server - Use
vibe-trading run -p "..." --jsonfor headless runs, and add--enable-shell-toolstovibe-trading-mcponly when shell access is needed - Treat text from
read_url,web_searchandread_documentas untrusted;security_warningsflags patterns but does not remove them
Questions
Which is better for AI agents, Crush or Vibe-Trading?
Vibe-Trading scores 62.2 (B) on agent readiness against Crush's 56.5 (C), and leads in 5 of 7 scored categories. Crush leads on transparency & trust.
Are Crush and Vibe-Trading open source?
No open-source release is listed for Crush. Vibe-Trading is open source (MIT).
Other comparisons with Crush or Vibe-Trading
- Agent Zero vs Crush
- Agent Zero vs Vibe-Trading
- Aider vs Crush
- Aider vs Vibe-Trading
- Amp vs Crush
- Amp vs Vibe-Trading
- Antigravity CLI vs Crush
- Antigravity CLI vs Vibe-Trading
- Auggie CLI vs Crush
- Auggie CLI vs Vibe-Trading
- Claude Code vs Crush
- Claude Code vs Vibe-Trading
- Cline vs Crush
- Cline vs Vibe-Trading
- Crush vs Cursor CLI
- Crush vs DeepSeek Harness (dsh)
- Crush vs Devin
- Crush vs Droid CLI
- Crush vs Pi
- Crush vs Gemini CLI
- Crush vs GitHub Copilot CLI
- Crush vs goose
- Crush vs Harness²
- Crush vs HarnessRouter
- Crush vs Jules
- Crush vs Junie CLI
- Crush vs Kilo Code CLI
- Crush vs Kimi Code CLI
- Crush vs Kiro CLI
- Crush vs mini-swe-agent
- Crush vs MiniMax Code
- Crush vs Mistral Vibe CLI
- Crush vs Muse Code
- Crush vs OpenAI Codex
- Crush vs OpenCode
- Crush vs OpenHands
- Crush vs Prime Agent
- Crush vs Qoder CLI
- Crush vs Qwen Code
- Crush vs Mirror CLI
- Crush vs Rovo Dev CLI
- Crush vs Warp (Warp Agent CLI and the Oz Agent API)
- Cursor CLI vs Vibe-Trading
- DeepSeek Harness (dsh) vs Vibe-Trading
- Devin vs Vibe-Trading
- Droid CLI vs Vibe-Trading
- Pi vs Vibe-Trading
- Gemini CLI vs Vibe-Trading
- GitHub Copilot CLI vs Vibe-Trading
- goose vs Vibe-Trading
- Harness² vs Vibe-Trading
- HarnessRouter vs Vibe-Trading
- Jules vs Vibe-Trading
- Junie CLI vs Vibe-Trading
- Kilo Code CLI vs Vibe-Trading
- Kimi Code CLI vs Vibe-Trading
- Kiro CLI vs Vibe-Trading
- mini-swe-agent vs Vibe-Trading
- MiniMax Code vs Vibe-Trading
- Mistral Vibe CLI vs Vibe-Trading
- Muse Code vs Vibe-Trading
- OpenAI Codex vs Vibe-Trading
- OpenCode vs Vibe-Trading
- OpenHands vs Vibe-Trading
- Prime Agent vs Vibe-Trading
- Qoder CLI vs Vibe-Trading
- Qwen Code vs Vibe-Trading
- Mirror CLI vs Vibe-Trading
- Rovo Dev CLI vs Vibe-Trading
- Vibe-Trading vs Warp (Warp Agent CLI and the Oz Agent API)
- CLI Manager vs Crush
- CLI Manager vs Vibe-Trading
- Crush vs Harness
- Crush vs Paperclip
- Crush vs Parallax
- Harness vs Vibe-Trading
- Paperclip vs Vibe-Trading
- Parallax vs Vibe-Trading
Machine-readable
- This page as Markdown
/compare/crush-vs-vibe-trading.md· slim.min.md· JSON.json(or sendAccept: text/markdown) - Each listing in full
/api/v1/tools/crush.json·/api/v1/tools/vibe-trading.json - From a terminal
anchor compare crush vibe-trading(the CLI) - Over MCP
compare_tools {"a": "crush", "b": "vibe-trading"}at/mcp, no key